Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
algerian-dialect-translation
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0060
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1933 | 1.0 | 66 | 0.0389 |
| 0.0614 | 1.99 | 132 | 0.0180 |
| 0.039 | 2.99 | 198 | 0.0131 |
| 0.0342 | 4.0 | 265 | 0.0084 |
| 0.0281 | 5.0 | 331 | 0.0072 |
| 0.0268 | 5.99 | 397 | 0.0068 |
| 0.0271 | 6.99 | 463 | 0.0067 |
| 0.0234 | 8.0 | 530 | 0.0059 |
| 0.0226 | 9.0 | 596 | 0.0061 |
| 0.0211 | 9.96 | 660 | 0.0060 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0